Summary - AlwaysSafe: Reinforcement Learning without Safety Constraint Violations during Training

less than 1 minute read

Published:

Discussion about the article “AlwaysSafe: Reinforcement Learning without Safety Constraint Violations during Training” by Simão, Thiago D., Nils Jansen, and Matthijs TJ Spaan. Published at Proceedings of AAMAS 2021.

Main points

TODO

More details